Flux-Claude-Art / README.md
prithivMLmods's picture
Update README.md
2bf7b90 verified
---
tags:
- text-to-image
- lora
- diffusers
- template:diffusion-lora
widget:
- text: 'Claude Art, An animated cartoon image of a man in a white collared button-down shirt and a brown apron. The mans arms are crossed in front of him, and he is holding a tablet in his right hand. He has a serious expression on his face, and his eyes are squinted. His hair is dark brown, and the background is a light green, with the letters U visible on the left side of the image.'
output:
url: images/1.png
- text: 'Claude Art, A cartoon drawing of a man holding a baseball bat in his right hand. The man is wearing a black jacket with a zipper on the right side of the jacket. His pants are a vibrant green color. His hair is a dark brown color and he has a serious look on his face. His eyes are squinted and his mouth is slightly open. The background is a vibrant red and black striped wall.'
output:
url: images/2.png
- text: 'Claude Art, An animated portrait of a black man with a bald head and dark eyes. He is wearing a blue and white striped polo shirt. His hands are crossed over his chest. He has a black tie around his neck. Behind him is a red brick wall. '
output:
url: images/3.png
- text: 'Claude Art, a digital painting of a black man with long dreadlocks, wearing a purple jacket, a red t-shirt, and a silver chain with a key pendant hanging from it. The mans face is adorned with a pair of aviator-style aviator sunglasses. His eyes are tinted blue, adding a pop of color to the scene. The background is a deep purple, with a few wispy white clouds floating in the air.'
output:
url: images/4.png
- text: 'Claude Art, An animated cartoon image of a girl with long blonde hair, wearing a white sundress and a wide-brimmed straw hat. She is standing in a sunflower field, with a basket of freshly picked flowers in one hand. The background is a bright blue sky with fluffy clouds, and a small butterfly hovers near her shoulder.'
output:
url: images/5.png
- text: 'Claude Art, A digital painting of a man with a rugged beard, wearing a thick fur-lined coat and leather gloves. He stands atop a snowy mountain peak, gazing into the distance. His breath forms mist in the cold air, and a faithful husky dog sits beside him. The background shows vast mountain ranges under a pale winter sky.'
output:
url: images/6.png
base_model: black-forest-labs/FLUX.1-dev
instance_prompt: claude art
license: creativeml-openrail-m
---
![asdfgsdfgv.png](https://cdn-uploads.huggingface.co/production/uploads/65bb837dbfb878f46c77de4c/bO4sXXaDJrvDAVeuEq7wq.png)
<Gallery />
# **Model description for Flux-Claude-Art**
Image Processing Parameters
| Parameter | Value | Parameter | Value |
|---------------------------|--------|---------------------------|--------|
| LR Scheduler | constant | Noise Offset | 0.03 |
| Optimizer | AdamW | Multires Noise Discount | 0.1 |
| Network Dim | 64 | Multires Noise Iterations | 10 |
| Network Alpha | 32 | Repeat & Steps | 28 & 3600 |
| Epoch | 22 | Save Every N Epochs | 1 |
Labeling: florence2-en(natural language & English)
Total Images Used for Training : 34
## Best Dimensions & Inference
| **Dimensions** | **Aspect Ratio** | **Recommendation** |
|-----------------|------------------|---------------------------|
| 1280 x 832 | 3:1 | Compatible |
| 1024 x 1024 | 1:1 | Default |
## Setting Up
```python
import torch
from pipelines import DiffusionPipeline
base_model = "black-forest-labs/FLUX.1-dev"
pipe = DiffusionPipeline.from_pretrained(base_model, torch_dtype=torch.bfloat16)
lora_repo = "strangerzonehf/Flux-Claude-Art"
trigger_word = "claude art"
pipe.load_lora_weights(lora_repo)
device = torch.device("cuda")
pipe.to(device)
```
## Trigger words
You should use `claude art` to trigger the image generation.
## Download model
Weights for this model are available in Safetensors format.
[Download](/strangerzonehf/Flux-Claude-Art/tree/main) them in the Files & versions tab.